Projects
![]()
No projects found
Investors
New
DAO Treasuries
DATs
Lend / Borrow APRs
Chains
Categories
Spaces
NEAR AI - What Did You Ship This Week? Ep. 6
Recorded: March 27, 2025 Duration: 1:06:42Space Recording
Short Summary
In the latest episode of 'What Did You Ship This Week?', various projects in the crypto space showcased their innovations, including GrowthMate's recommender systems for Web3, Nillion's privacy technologies, and Jutsu's TypeScript SDK for Near AI, all contributing to the growth and evolution of the blockchain ecosystem.
Full Transcription
Good morning, good afternoon, good evening to everybody.
It's good to see you here.
Frederick, do you mind making me bigger if possible?
This is the sixth episode of What Did You Ship This Week? My name is Cameron Dennis. I am just
here to quickly introduce everyone, and then I will be giving Near AI's update at the very end.
Just for context, at Near AI, I'm responsible for all external integrations and partnerships,
and this is just something we run every week.
It's essentially a decentralized ecosystem standup.
And the whole point is for people to share what they built.
It's pretty straightforward.
Everyone has around six to eight minutes.
I pop up on the screen when you have about one minute left.
If you're going to share your screen,
please only share the tab that you plan to share.
We've been through this before.
Let's not make that mistake again.
So without further ado,
I'm just going to quickly introduce the agenda for today.
Giving a quick intro as I'm doing now,
and then we're going to pass it off to Mohamed from GrowthMate,
and then Nico from Million,
Zahid from Jutsu,
Andrew from Doppelgangers,
Peter from JS and Rust,
and then Jeevan and Uliana from Instant Apply. And then at the very end, I'm going to be talking about some of the
stuff that is cooking on the Near AI side. But without further ado, Mohamed, I'm going to bring
you up to the stage. You have about eight minutes to talk to everyone about what you should this
week. Just want to quickly flag, introduce yourself, introduce what GrowthMate does, and then talk about your recent developments.
Okay, awesome. Hi. Yeah, so I'm Mohammed Ali from GrowthMate.
We build recommender systems for Web3 users.
And so what we are trying to solve is the discovery problem. At any given time, there is so many cool things happening in Web3, and it's usually hard to
stay up to date with everything that's happening.
And so here, let me say, maybe I can share my screen, and I can show you.
How does this work?
Let's see.
I guess now you should be able to see my browser, right?
Yeah. Okay, awesome. So it's usually traditional that every ecosystem
has some kind of directory where they list other projects.
And it's usually great to find out which projects exist.
But then it's limited to just giving me a project logo,
project name, and some short description.
And for me as a user, knowing that, OK, this is a project logo, project name, and some short description. And for me as a user,
knowing that, okay, this is a DEX or this is like a linear, I can stick, but then
it doesn't expose the opportunities from within. And so it's just like, okay, good to know that
the DEX or landing platform is there. How can it help me? and so we go a step further and uh we have our own bots that collect
all opportunities from within the projects um and so for instance here you can see we have like
by the way we are multi-chain um but for near yeah you can see that um it's aware that from
rea you can provide the Bitcoin liquidity today.
If you can lend your SDC for 7%, you can do a bunch of stuff.
You can trade meme coins here.
This is how much you would get for lending your DAI.
You can earn points on all stake.
Anyways, we expose the opportunities from within each project.
And so we use this to provide personalized recommendations
to the user and to tell him, like, hey, based on your on-chain data,
here are some cool matches.
And so we recently added this as the Near AI agent.
And I think now you should be able to see, yeah, our agent, it's under a growthmate.near
discovery agent. And so for instance, the agent is aware of the user's transaction history in a,
like a human readable format. So it knows that, yeah, I sent some tokens from GrowthMate to SputnikDAO. Yeah, it knows I received some tokens.
And yeah, it's like aware of my transaction history.
It's also aware about my portfolio holdings.
So like I have some near, I have some USDC,
and I don't have any positions in this specific account.
And so based on this data, it's able to give me
like cool matches from the opportunities here.
So for instance, it like saw that I have both USDC and near.
And so the first recommendation was,
hey, by the way, you can get like really high yield
by LPing into the USDC WNIR pool on Rea.
Or because I transacted with the Shih Tzu,
though it know that, OK, it could be relevant to go
and trade meme coins on meme cooking.
And yeah, this is basically it.
I expect this to be really interesting to other agents
because many assistants
would be interested in providing such discovery features
to their users.
And yeah, I would love to know if you have any questions.
Oh, I think one last thing is you can configure
like your data here by creating an element
on our platform. And so here you can have access
to some filtering options so you can say i want i want to protect users gambling so you can just uh
like uh blacklist gambling and so all gambling things will not appear in the first place
how do you define gambling like that's such a you, you know, a lot of crypto is debatably gambling, even if it's not, you
know, traditional gambling.
So how do you, how does the agent actually define that?
Yeah, yeah.
Well, there is definitely some objective measures that go in here uh but from our point of view we always try to uh narrow down
uh like to the closest category and so for instance if something is a dex or a burp then
it would be labeled as a burp or if it's a meme coin trading then it is it will be labeled as
meme coin uh trading platform and so so um, gambling would be .
Got it. How do you manage that taxonomy? Like of all the
banks and everything?
Yeah. So we are getting data sets from other providers and
we merge them into our own schema. And then we have to create a new category
and then add to that.
We have a big category for Baychain,
and the categories that would identify NFT subcategories.
So that would be like AMM per coin trading platform.
Yeah.
Super cool. Awesome stuff, man.
What's the best place for people to learn more about
what you're doing and stay updated growthmate xyz uh also on twitter growthmate underscore xyz
amazing um is there any final thoughts uh the parting comments well please reach out if you
think that this could be helpful to your project.
Awesome. Who's your target market exactly?
For the Near AI agent, it's mainly other agent builders who want to expose this through their assistance.
We also have like a standalone chat interface under chat growthmate XYZ.
And here you can see everything is like more retail focused.
It's, you know, the formatting and display is more refined. Super cool.
Awesome.
I'm going to DM you.
I have a bunch of questions that shouldn't be asked in public.
So I will DM you.
And next up, we have Nico.
Thank you, Mohamed, for joining.
Hope to see you soon.
I appreciate it.
All right.
Nico, can you hear me? Hey, hey. Yes, sir. Yes, sir. Yep. All right. Nico, can you hear me?
Hey, hey.
Yes, sir.
Sweet.
It'd be awesome if you can quickly introduce Nillion, yourself, and what you shipped this week.
Yeah.
Yeah, my name's Nick.
I've been working with Nillion for about two and a half years now on the engineering side.
I've been with Nilian for about two and a half years now on the engineering side, and we built a whole bunch of really cool stuff.
And primarily what Nilian's focus is, is privacy enhancing technologies.
So what that means is creating composable solutions that can work well together to add privacy and other secure aspects to your guys' project as builders. So one of the projects I've
been working on lately is on the agent side. We have different initiatives happening with
like TEEs and secure inference and things like that. So stay tuned for those kinds of projects.
And you can always look up what's happening
on our GitHub page.
And we have a super active community
where you can learn more.
And today though, I'm gonna talk about the secret vault.
And let me share my screen here.
I'll see.
It's giving me options.
I will do, I'll start with this one over here.
Okay, so Secret Vault.
What our Secret Vault is, it's a distributed database as a service,
but it's distributed amongst trusted infrastructure runners to like each one is going to contribute a host so that they can together, you can compose a cluster and your cluster would be M of N or you have certain number of nodes that you select from these different providers that have particular characteristics that you like, for example, geo latency and things like that. And so you can pick which operators are
going to be your Nelian secret vault. And then when we're creating, you know, when we're encrypting
and saving data to those hosts, they get secret shared across the different hosts,
which means that not one of the hosts has data on their own to be able to, they can't view it.
Like even that operator themselves can't actually expose the data, leak data, without total
collusion from enough of those particular parties.
So that's a really cool thing.
And what we think that this is valuable for agent builders is that it gives us a way of using distributed storage
or using a database service that's distributed, that's Web3 friendly and very much focused and to provide you
with some extra privacy enhanced technology there. So the demo that I wanted to show today,
I was using the Langchain extension that the Near team has built to wrap around the Coinbase agent kit.
And so what that's done is it's given me this orchestration layer in Near to be able to activate the Langchain workflow.
And that gives us some really cool things in the agent.
And I think I need to stop this share and start another one.
So let me do that really quick.
Window.
I'll do this one.
Okay, so on my screen, I'm just going to walk you through some quick code so that you can see what I think is the ease of using these patterns of the agent kit.
And the, or I should say the length chain tooling that is created, that's going to be an interface, like an agentic interface, maybe a low low code maybe vibe coding interface to using
our secret vault so um let me close that guy so everything's pretty boiler plate plate here but
i'm going to show you where i started was just by giving this prompt where um i'm defining what that, oh, let me back up. What am I doing? So I'm creating a trader. So maybe it's,
I don't know if it's similar to Muhammad, but I was really interested in what he was doing there.
So I created a fully autonomous agent that's going to take a daily report that's generated
from a scraper that I made. And it's going to pull, like I'm using the secret vault to store my trading
preferences. So it's got my risk tolerance. It's got any of my information. This is what you're
seeing on screen here is how I'm describing what that risk profile is. And so this is my schema
definition. All it is, is just natural language, right? So you're able to describe, I say, create a basic schema in the secret vault,
and then I describe what that schema is.
Now, the secret vault, like what the schema actually is,
it's like a MongoDB style schema where it's a JSON schema.
And the way to designate which of the fields are encrypted has some extra structure.
And so this agent prompt or this tool will handle that for you, which is really nice.
It'll decide based on how you describe it, whether or not it's private.
You could say this field is private. You could also say this field is financial, this, you know, like whatever kind of terminology, there's some built in to the tool itself to do that for you. So after that
schema is created, then you could do different operations on it. So in my case here, I say,
you know, here's my risk strategy. And I'm saying that I want to be an aggressive trader.
So the aggressive trader, I also described in these terms. So it knows what I mean saying that I want to be an aggressive trader. So the aggressive trader, I also described in
these terms. So it knows what I mean by that, right? So if I want to update my profile to say
that I'm balanced or that I'm conservative, I can easily update that record and make it so.
Then the interesting thing happens. Let's make this a little more readable. So here's my agent task.
My agent task says fetch the data from the risk profile.
So the agent is already wired up to the tool that knows how to find my risk profile and decrypt it and present it into the context of the inference.
So it just handles like this secret data. I don't want my profile stored
locally. I don't want my profile accessible to others. I don't want them seeing because maybe
I'm a whale. I don't want them seeing what I'm doing. And that's my own private,
my desire there. So the agent context is, it's just all prepared with
the data. So now I'm, I'm just giving it kind of instructions on how to work with that profile,
how to use my crypto report to create a strategy, and then it's executing trades. And you can see
here, I mean, I've been running this for, you know, several days. I just have it running, you know, just kind of in a loop. And you can
see that it's been busy doing stuff for with my wallet that I have attached to this. So
this is all real output. It's really happening. It's really it's trading on mainnet. So it's
interesting. And, you know, like I see see that there's also on the agent hub,
there's something kind of similar,
which I think is pretty cool.
But adding in that secret vault piece,
that should have a primitive, right?
A data primitive that you can have
where you can deploy service and have this,
you know, software service, but preserves privacy and, you know, in a new way.
All right. I think that's all I got for now.
Well, privacy is an absolute prerequisite for any of this agent stuff to work.
We have Xtrace on every once in a while on this call as well.
This is the thing.
If whoever solves this problem actually can personalize agents,
and no one's ever going to want to use agents if it's not actually personalized to you.
So I think this is really, really cool.
Yeah, anything you want to add?
No, I think you nailed it. It's our passion, it's our mission.
It's what we've started out to achieve.
And so this is one of the areas that we see
that's relevant to today's,
the excitement of using agents and even Vybe programming.
So it lowers the complexity of integration, but it also offers such a significant piece of privacy technology.
I'm so stoked.
Looking forward to actually getting this integrated in the hub as well.
So thank you, Nico, for coming on. We do got to get moving on to Jutsu from, sorry, Zahid from Jutsu.
Zahid, bring you up on stage. Zahid is building a lot of stuff.
And so Zahid, I'm gonna let you kind of like manage what you want to talk about today.
But first, intro yourself, intro Jutsu.
What did you show last week?
Okay.
So, hey, everyone.
I'm Zahid, founder of Jutsu.
And in Jutsu, we are working with Near AI to kind of build a TypeScript experience.
uh typescript experience so since we started the project our goal is to build a system that
uh a developer can come in and kind of start building a near ai agent and deploy it in minutes
not hours so we made some progress in in the typescript sdk and i will show you a demo
and then i'll show you another project that I'm working on.
But let's start with the TypeScript demo.
I'll share my screen.
I'll share my entire screen.
So make it bigger.
So the way you will start using Near AI TypeScript SDK is just simply type npm install the Near AI TS CLI.
So that will kind of install the npm package locally.
And then to create a project, you will just say npm near CLI create.
That will create a local project.
You don't have to do anything.
And then you can go inside your project
and you will see the familiar things like Python projects.
So you have a agent.ts and metadata.json file.
And to run an agent agent simply you just run
near aits run you don't have to do any other things so it's as simple as it and then you get a common line interface that you can you can interact with your agents
And you can update your agent TypeScript code, add your own functionality.
It is not one-on-one comparison with Python yet, but we are working hard on making these
two frameworks work the same way and all the functionality.
So now we are asking something.
And then when you are done, when you are ready to deploy,
all you do is just near AI TS upload,
and that will upload your project to the near hub, AI hub.
And then when it deploy, you get a link that you can go and check your agent.
So one important thing here today, you can upload your TypeScript project to Hub,
but you cannot use the Hub UI at this moment, but we are working on kind of making that one work.
So hopefully by next week, when I come back,
it will be end-to-end where you can deploy
and you can use the hub
and you can interact with your agent.
So I think like the goal since the beginning
is to kind of from zero to one in a minute.
So that's kind of what we are working on.
And hopefully next week, we'll ask the community
to start kind of using the TypeScript SDK
and give us feedback and it's for you.
And I love to work with community
and then kind of build the best SDK possible.
Next few minutes, I want to show another project
that was part of like a near useful agent hackathon.
And thank you, Cameron, for running that hackathon.
So that useful agent is becoming more and more useful.
So I will show you a little bit of demo.
So this is the agent that we build in the hackathon.
But now, since after that, like we improved the media, the generation of the images and
video quality probably 10 times better now.
Like typically like this, for example, this is a generated image, but it's almost indistinguishable from if you would record a video by yourself.
So that's probably 10 times or more improved than the last version that we had. And the other thing we added is a lot of small and medium businesses already use Canva. And we had a lot of requests from the
people like they have all the assets for their businesses in Canva. So if they could use Canva
with Post. So now you can. We are now in a process of getting approved from canva
because it's in a canva marketplace so we need approval so hopefully by next week it will be
generally available where people can start kind of bringing their asset from canva and then uh
make their uh social media automation and save a lot of time uh so that's yeah that's that's kind
of the update uh from the post side and i would encourage like a go and check out like app.post.ai
and give it a try like uh if you are not posting today you are probably missing out a lot of
day, you are probably missing out a lot of exposure that you would get as a founder or
as an engineer or as a builder.
I think one thing I learned last one and a half year is it is great to be a great builder,
but you also need to build in public.
And as an engineer, like I don't like to be in public, but like that's why this kind of automation and AI agent is there for kind of like be a digital twin of me and then do the social media for me.
So, yeah, give it a try.
Yeah, this is amazing.
I'm using Post these days.
It's working.
And speaking of digital twins, we have Andrew from AppleGave coming next.
Before, I want you to understand, you integrate with the extra web apps. What exactly is that process like? You got to get approved.
How do you even start that for a lot of builders here that might not know?
Can you repeat the product?
How do you want to go integrate with Canva, how people using their Canva accounts interact
with Post.
How do you even start that process?
You just use their API, you have to get approved, what does that actually look like?
So the integration process is you have to create a kind of a sign up with the developer account.
So you have to build the app there and then the API integration.
You have to build a third party API integration.
And then when you have it ready, then you have to submit your app.
It's more like when you deploy a mobile app in App Store.
So it's similar kind of process.
And then they will do the review, which makes sense.
And then they'll list your thing in their media.
And then the benefit is, as a user,
you don't give us any password or anything.
So it's like a third-party integration.
So it uses their APIi so you are safe we are
safe and for builder i would recommend another thing is try to build those integration because
it become a distribution channel canva is one of the largest uh design today. So if you're building something else, maybe partner with other ecosystem
and that gives you more exposure and also validity, right?
So like, so yeah, so the process is in short processes
like App Store, if you ever build a app,
have to go through the review,
then get listed in their ecosystem. Super exciting stuff.
Love to hear how that process goes with Canva for next week.
Going to bring on Andrew.
Zahid, is there anything else that you wanted to add before we hop off?
Give it a try.
And if you have a TypeScript SDK, just reach out directly, DM me.
I'm available, and I'm happy to work with you.
Beautiful.
P-O-S-T-T dot A-I.
Go check it out.
Thank you, Zahid.
Bringing on Andrew.
Andrew, how you doing?
You've been here before.
Introduce Doppelgangers, yourself.
What did you do last week?
Hey, Cameron.
Hey, everyone.
My name is Andrew.
I'm a founder and CEOo of doppelgangers
at doppelgangers we are bringing we are building user-owned ai so anyone can create their own
personalized ai assistant that well do stuff for you um we have uh recently added a voice feature so now you can not only
chat but you can also talk to your personal ai and on top of that we are creating digital twins
so think of it as personal AI versus public AI.
So your digital twin is basically a representation of you.
You can put it on socials.
You can make it go to a podcast or to Twitter spaces for you.
It's basically your digital twin. And on the other hand, personal AI is secure,
stored on your device. And well, 100%. I mean, both of them are 100% yours. You are the one
who controls what goes in. And yeah, user-only AI is here.
And yeah, user-owned AI is here.
Awesome. What did you ship last week?
Voice.
Voice.
Cool.
Do you have a demo?
We have a voice feature within our agent.
You can talk to it.
We also can create a digital twin of your voice.
The more you talk to it, the better it becomes.
So check it out.
DoubleGanger.ai, App Store and Android are both live.
Can you show us?
I'm fortunate that this is a thing that's a mobile sharing feature.
And all of them are on mobile app.
So I would love to.
Can you pull out your phone and show us?
Sure. Sure.
Let's try it.
It's okay.
The demo gods, I'm feeling they're with us today.
So they're with us.
Let's chat and fine-tune how it responds.
Hey, how are you today?
Feeling great.
Thanks for asking.
Rocket, how about you?
Anything fun or interesting going on in your world today?
We are actually on the live stream right now. Can you say hi to everyone?
Can you say hi to everyone? We are on the live stream right now.
absolutely party popper hey everyone watching the live stream waving hand hope you're all
having an amazing time let's get ready to rumble and dive into some awesome crypto and blockchain
discussions lfg flexed bicep sparkles i love the sparkles the sparkles at the end really made it.
That's great.
So what's next?
A little bit of a video,
but we are mostly working on integrating all these features like voice into Near AI.
So more integrations on the Near AI side are coming.
Basically, within our app,
your personal AI agent will be able to use any agent
in the near AI discovery tab.
So eventually, it will be able to book you a flight,
buy your headphones like Ilya presented last time
and get you an Airbnb.
And generally speaking, any integration that will be live via uh near
ai is going to be available on your device with your personalized agent we have a wallet integration
near wallet integration already in place so you'll be actually you'll be able to just ask it to buy stuff or get your stuff or book your stuff and it will just go ahead and do it.
I want it to manage my LinkedIn account for me in natural language.
I would pay money for that, actually.
So this is great.
Love to see it.
Is there anything else that you want to, I guess, say before we hop off to Peter Salomonas, who is next?
I'm sorry. Salomonas, who is next? Yeah, guys, download our app. We
require more feedback from our users. We are constantly improving the user flow and design so doppelganger say hi available on app store available on google play join join
cool uh before we hop in 30 seconds or so any advice for current agent builders to get their
agents actually available on the app store like you did it i mean, it's very straightforward.
You just follow the policies.
To be honest, for me, App Store was easier than Google Play
because Google Play introduced a whole bunch of new policies
where you do it when you need to run close testing
with a bunch of people, which is weird.
And App Store, you just call through approval.
It's a two-way communication.
If they don't like anything, they tell you what's wrong,
you fix it, and you just go live.
Got it.
Cool, man.
Andrew, thank you for joining as always.
Sure, guys.
See you soon.
Peter, welcome, welcome.
Thank you. Thank you.
Great, great year.
Thank you for having me.
For those who might not know Peter, he ships so many really compelling things, primarily in the WebAssembly space.
He's written books. He's constantly on the cutting edge.
So I'm really excited to hear what you have to share today.
But before we get going, just as a reminder, introduce yourself any further, what WebAssembly music is or anything else that you're working on, and then exactly what you shipped last week. Demos are preferred, but demos are preferred.
Yeah, so I'm Peter, and as Cameron already said, my first intro into the NIR ecosystem was the WebAssembly music project, which I've also had been working on before then.
But the purpose was to be able to publish music
on the blockchain.
So actually a full piece of music is stored
in a small WebAssembly binary with all the instruments,
all the sound generating, and it plays music,
this WebAssembly music executable.
So there are some NFTs on that that but today i'm going to talk
about something completely different i'm going to talk about the js in rust project and now um oh This is, I just have to allow my browser to share.
So let's see.
Sorry about this.
No worries at all.
It happens to every single person.
Yeah.
It says I have to open system, quit and reopen.
Oh, okay. I will be right back. Sorry about that.
Oh, good. I can...
Actually, do we want to move on? Do you want to come back to you, Peter?
Yeah, yeah.
Yeah, yeah.
Perfect.
Okay. Sounds good. We'll hear from you soon.
Yeah, yeah. All right. Jivan, are you ready to rock? All right. Okay. Sounds good. We'll hear from you soon. Yeah.
Yeah.
All right.
Jeevan, are you ready to rock?
All right.
Cool.
And Uliana, are you here?
Yep.
Great.
Welcome.
Welcome.
It's good to have you guys back.
Really excited to hear the update, especially after your conversations with Silverstream
over the last week.
I've not gotten the update yet, so this is part of my update.
So, yeah, we'd love for you guys just to, like, reintroduce yourselves.
What is Instant Apply, and what have you guys been working on over the last week?
I can start off.
I'm Jeevan.
I'm a CS student at Minerva University.
I'm doing CS and Econ.
And we built Instantly in the last useful
AdSense hackathon, same as Zahid, and we got a sponsor award from Silverstream. So we have
been working with them to build the app further. Uliana.
Yeah, I'm Uliana. I'm also a CS major at Minerva University in my third year. And the idea
behind InSignApply is is as students we struggle with applying
to internships every year and a lot of our graduates also struggle with finding jobs
post graduation because you have to send out like thousands of applications literally not even
exaggerating and so we decided to build an app that would allow you to do exactly that in just one click of a button.
Yep.
Jyvon, do you want to go about the?
Perfect.
So this is the timeline.
I think we started with the hackathon in 14th and 15th March.
Literally two days ago, or like one day ago, we got 20 beta users for the app.
And today, or any study, we are completing applications for our first user. And while
also completing the application, like based on their experience and the conversations we're
having, we're also extensively changing the app, both in the front end and the back end. And one of the major things was
our resume parsing. So when they upload their information we were using PyPDF and not really
working well. So we are now using Xemini to parse their resume which is doing much better for like
all the sections. And we also changed our job recommendation system.
If you are in CS,
you might want to be a software engineer or
an ML or go multiple places.
Based on all of that, it recommends job and with a much better mat.
We also changed our frontend.
Since the last time, I think we only had one HTML button, nothing else.
We changed a lot of our front end.
So this is an example on the job recommendation.
We generated a PDF for our first user
just to show them what kind of jobs
we're applying for them to.
And it also gives you a match score and a recommendation
to apply or not, and what skills are matching for you
and the URL for the job.
And for jobs that do not really match and what skills are matching for you and the URL for the job. And for jobs that do not really match
and what skills you need to develop
to be able to apply to these jobs.
Or if you have other experiences,
you can change your resume or the information
you have on our profile so we can apply it better.
And it recommends that you skip and don't apply to these jobs.
Olena.
Juliana?
Yep, I'll now present to you our better front end
and parsing.
Just a moment.
Okay, we'll start with a login.
Just... You log in, I created a freshly new user, it's completely empty, so you go to profile,
you don't fill out anything yourself, you add your resume. it um it parses the resume that takes a bit of time because it does the calls to ai but um the
results are really nice so we get to actually see all the okay all the details i did not type any of
it myself this is not hard coded or anything name summary um the text of the resume itself just for, you know, when you upload a file and it has been a month since, you don't remember what's there.
Professional experience, personal projects, description of the personal projects, relevant skills, all of that.
Certifications, demographic information, because it's often asked in the Java applications,
but not so important.
If you want to change anything, you can edit it manually,
like, I don't know, right?
And you save it and it's changed.
So now for those of you who have been here
for our previous shipment,
I am proud to present to you a prettier button
now you can just press this which looks significantly better than the previous button we had
and it will apply for the jobs um yeah i'll not be doing that right now
um i think that's it johan do you want to add anything
yeah okay i think for now we're oh yeah i have one and so i think uh one of the other updates
we wanted to share uh like in our progress what we did last week was a lot of applying for vc
findings uh collecting the applications making the slide deck, and sorry, and preparing the demo that we can share with like potential basic findings or summer grants.
Yep.
Incredible stuff. How do you guys manage credentials? Like, you know, you're logging in, like how are credentials managed?
So the first thing right now is this database, the login.
A toffer problem we are facing right now is when we apply to jobs, they often require us to log in on behalf of the user.
And so we might need like their email, like the secondary something like a quotes and stuff like that
so for our first user uh for all of those we created a news email account so we can
like get those like codes from them but i don't see that being a more sustainable thing uh so
the likely option is we when they have the tool all to themselves, they might need to upload that for each of those websites
which ask them for them.
But yeah, that's something we are thinking of.
Well, maybe Nili, you can help.
Yeah, Uliana, go ahead.
Oh, yeah.
I just wanted to add quickly in terms of how our login works.
It's just a Flask login.
So I'm not sure if that answers your question, but they back largely Alaska.
Got it. Yeah, I guess it was more on like the, if you are logging into other sites that like,
you know, needs to like, do you see those, you know, passwords and plain text? Nico might be
able to help you there. So more to come on that. But is there anything else, guys, that you want to add before we pass it back to Peter?
Where can people learn more about the projects?
Where can people learn more about you?
Love hungry young builders.
That's always, you know, this is one of the first projects, I have to say.
Like, you know, another project, another project, another project.
You guys can build billion-dollar companies.
So, yeah, where can people learn more about you and stay in touch along your journey
uh so yeah the app right now is open source on github uh it's called instant apply i'll
share the link as well and for both of us we are in the near uh the telegrams uh and
we're also on london i'm like just even cs on linkedin i'll share the links
uh and you know happy to chat about this
or if we could have more suggestions on that.
I'll also share the link to my LinkedIn.
And while I'm in the same Telegram channel,
I think it's Liana underscore one for me on Telegram.
Yep, happy to chat.
Awesome guys.
So good to have you here.
Now hope to see you guys soon.
And yeah, best of luck for next week.
Peter, bringing you back. Howdy, howdy.
Yeah, yeah. New computer, but now you can see the screen. So I will go back to where I left off and what i'm going to talk about today is this project called json rust
which is basically letting you add javascript on top of your rust smart contract so the contract
we're going to look into today is a web for and a fungible token contract which allows you to create a website. But first of all, it's this web application here
where you have a client to these tools
that you also have the source code for in this project here.
So you can find all the source code here.
And this particular feature that we shipped last week was
was not a very big one it was just about getting these fungible tokens that we have here
for being able to use also this chat gpt feature which is going through a proxy because that allows you to kind of charge for the ai
conversation by using this fungible token so we can say now that i want to buy rice tokens and
we can ask the near ai for that and it will then when, and we have to confirm it, and we actually have to confirm it again.
And that will, if you say, okay, now you will be taken to the wallet and confirm.
So, and that will give you these tokens for using ChatGPT.
for using ChatGPT.
But let's also try the other interesting part,
which is about running JavaScript
and also creating a Web4 site.
So what I want to do now is to create this new Web4 account.
So I want to create a new Nier account, really.
I would like to create a new web4 account and let's it can be named web4
three four demo uh near let's remember that name and we can ask the near ai for doing that
and we can ask the near AI for doing that.
And this will, of course, require some storage
for deploying the contract.
You will have the key so you can delete account
and get those near back.
But let's just create it and confirm with a wallet
and approve.
You can see now it will actually call this web4 factory
and create this new account.
And we can approve that transaction.
And as that thing said, we now have a new account.
And we will also soon get a website up here but we can see now the account
was not found but if we now reload it it should be there but we can see also that it's nothing
there yet so and also in the local storage now we have the keys for for that particular account we can see it here so so that you can save and and use if you
want to delete the account or access it in any way and now we can also try to use since i already
have some rise tokens we can also try to use chat gpt for deploying some content to that web4 site. So let's do that.
Create a web4 page on that says hello world.
And we can ask.
And now it starts the chat GPT conversation.
It will take some fungible tokens
and we can have them refunded those unspent after and
now it's deploying that javascript so what it actually done was to to create some javascript
here that is having some html payload and let's go to that web page and see what happened. It says, hello world. And can you also display the current time on that page?
And we can, again, see how we should be updated here right away.
Yeah, we got the current time and there's also a in-browser simulation here.
So can you also add the current account ID
and run the simulation here first.
And let's ask for that.
And we can see it now,
it actually runs the JavaScript that it created
and it posted that to the contract.
This is how it would look like and now it asks us to deploy it because it's not updated here yet but
let's say yes to this and again it will run the deployment
um and again it will uh run the deployment um and it's deployed successfully deployed and we can see
now if we we have the current account id and we can continue like that uh uh so so actually the
javascript can you show me the web page javas JavaScript code just to have that also?
It looks like this.
So it's actually this web for get function that is implemented
that you're able to send to the JS in Rust contract.
And yeah, so that's basically basically it uh that i have for this that's the most recent development
on this project here the plan is to integrate it also with this arise portfolio uh report so that
you can actually uh talk to this application when you are tracking your Nier account activities.
So that's the plan ahead.
And now I'm not sure.
Yeah, you are already there, Cameron.
I mean, I don't mind this taking much longer.
I want to better understand your whole vision here.
You've been programming on N here for quite a while,
and I kind of see all these projects slowly kind of coming together. So I just take a couple minutes
just to kind of explain like, I mean, I'm sorry to start from square one, but like why WebAssembly?
You know, you wrote a whole book on this, i'm assuming um and then also like some of these
other projects that you're building and kind of how you see the vision kind of coalescing yeah yeah
so web assembly is of course uh uh this compact uh binary formats and you can and you can create uh
code in many different languages you can create this very efficient binaries that lets you execute
this in the web browser, on the server, and we also see on Nier. That was what I was looking for
when I found Nier. Actually, I wanted to see a blockchain that used WebAssembly as the smart
contract binary because I thought that had to be the ultimate thing. And then I found air for that.
And I've already been many years working in the WebAssembly space
with several different projects.
And when it comes to what I really want to do is this music project.
That's how it's all started.
That's been focused around that all the time.
It's about also using WebAssembly for live coding music.
And I would really love to show you that also one day.
There are several videos on my YouTube channel about it.
But the thing is, you can live code music.
You write your
music in code and it compiles to a web assembly binary on the fly and and and you can just evolve
your music your instruments uh and adjust your code and you can hear the results instantly in
the music and and now that we have got AI, this is a perfect match
because then you can actually use the AI
for writing that JavaScript code,
just as we saw here with the web4 page.
So this is kind of just leading up to my next,
where I want to go next also
is to have this AI generate music.
And one thing that is also mentioned in
this written about this book is to to write um instrument plugins uh which all the music producers
use in all the music you found there on on stage wherever and and and um you can write that in the
browser you can use the ai to express what kind of sound you want
and and and then you can use nfts for kind of selling the unique sound to to music producers
and you can and they will have ownership to it so i think that's a great use case for for the NFT. And the WebAssembly binary is compact.
You can ship it.
You can have this also very tightly connected to the NFT.
And then you can also actually use that
in the music production software that is common today.
So yeah, as you understand, my kind of vision here and my passion is a lot around the music.
But being into the near space, also lots of other things have to be solved.
So that's why I'm into this accounting system.
That's one of the things.
Web4, we want a website for it.
The JS in Rust was also just part of fulfilling this, yeah,
the way of being able to use JavaScript to customize,
and JavaScript is also part of that music project.
It sounds like you're building a new internet.
You're kind of addressing every piece of the stack here,
sort of all using Wasm.
So it's incredible.
Yeah.
Well, so cool.
Peter, what is the best place for people
to follow up with your progress?
I understand you're most of the time busy shipping, which is why we want to host some
of these spaces is just like give these builders who frankly may not even love posting on Twitter
and all this other stuff, the platform.
So when you're not here...
Thank you so much for the opportunity to present here. And yeah, like you say, going on Twitter and post,
that's always, you know, taking time from actually building and shipping stuff.
But I love this previous talk here about this thing
that can help you with the social media, I think.
We all need it.
Well, yeah, where can people learn more uh so my my twitter is where i'm posting but i i would actually recommend going through my
youtube channel where i have uh videos showing all this that i also just showed with the web for
the json rust but also the web assembly music There are some videos of the showcases from this book that I have, and there's
also a chapter in the book about Nier Protocol, and also about this
Jason Rust thing. So that's also
if you look up that book, that's also a
good place to
learn about
what's the name of the book
the name of the book is
building and deploying
web assembly apps
and it's funny I
haven't got the hard copy yet from the
publisher so I
don't know I've seen people have bought
it and they have it but
not even the author that's kind of So I don't know. I've seen people have bought it and they have it, but I haven't.
Not even the author.
That's kind of hilarious.
So plenty of places for people to learn more.
Thank you so much for coming.
Would love for you to come on again.
We'll do this every week.
So whenever you feel ready to give another update, you're welcome back whenever.
I'd love to.
I'd love to.
Thank you for having me.
Thank you for having me.
Awesome.
Awesome.
Thank you, Peter, taking you off.
Thank you, Peter.
Taking you off.
That concludes all the, I guess, presenters today.
I am also going to just kind of give you guys a quick update on what I've been cooking.
The whole Near AI team, by the way, is primarily focused on building the most useful assistant in the world,
essentially turning every app into a super app
through a network of agents that are all verifiably private.
And the inference that those agent builders need
is currently free.
So if you are an agent builder,
you can get free inference.
Pretty cool.
That's one of your main costs.
And then through the assistant,
we will drive demand for your agents,
assuming they're useful. And that is drive demand for your agents assuming they're useful
and that is my job is to ensure they're useful and so right now over the last week i'm very focused
on hiring a team this team is primarily just going to include a director of ecosystem engineering
think of it like all external integrations and a marketing team, just like one marketing manager and maybe a social media management intern. But right now, it's all me. So I need to scale a team
because that's ridiculous. Next thing is really working with Nillion and Nexttrace on the encrypted
memory stores. This again is an absolute prerequisite to personalize your agents.
Critical. We already talked about that. We're also just on the kind
of internal Newer AI side, formalizing all of our success metrics, all of our KPIs, OKRs,
all that really, really fun stuff to hold each other accountable. And then other thing is we
are exploring adding more data sets to the Newer AI hub. Would love more feedback on what kind of
data sets you might be looking for.
We're right now on the hub.
It's primarily just like near rust contracts, and they have been used by teams building like auditor agents and other things,
agents that can sort of streamline the auditing process for your smart contracts.
But I'm actually really, that's cool.
Don't get me wrong.
Awesome stuff.
Want those people to keep building.
But I'm really interested in having an agent
that can audit other agents to check
for any security vulnerabilities, any data leakage,
anything else as a really critical piece
of the discovery process.
So before an assistant is able to go connect
with another agent, I wanna make sure
that that agent has been verified.
And so we did post this request for proposal to get AI security teams to
build this agent. We reviewed a lot of them. We had like probably like eight really great
submissions. And now we're sort of moving forward with, I guess like two of them, one and a half.
It's kind of a weird thing because like we need more useful agents hosted on the hub.
It's like security is always this sort of like secondary thing to a lot of teams, but
it is a primary thing for us because we will be managing keys and money.
So very critical.
So hopefully in the next coming weeks, there'll be more information.
I don't want to prematurely share too much about the architecture of this because I want
the team that is actually building it to do that. So more to come on that, but making progress on the auditor agent side of things. Next thing is
the house of stake. For those who might not know, the Near Foundation is very committed to
decentralizing the Near Foundation. Over a year and a half ago, we started an initiative called
the Near Digital Collective to essentially run an election to determine who can actually decide on how money gets allocated.
There was about 10 million USD of near allocated to that treasury. And this was a crazy experiment
that didn't end great because there was a lot of vote buying and a lot of crazy things on
the governance side but guess what that's not stopping us we are doing version two and this
version two is a little bit more top down than version one and is going to need agents that
help with the governance process governance is an incredibly difficult thing humans are inherently
biased i can say for so myself like
i am biased to proposals that i can actually read and understand so english and a little bit of
spanish if you send me a proposal in chinese i'm biased i'm not going to be able to read it and so
how can we actually create these agents that can streamline governance for the people who are
deciding on how money gets allocated.
And so this is really important, really big. This is all going to be done through the House of Stake initiative. And I'm working with House of Stake and also Metapool. I have a call later with
Claudio, the founder today, about how to streamline governance inside of Metapool, which is an
amazing liquid staking app that is very committed to decentralization
through a DAO. And so they have a very active DAO. How do we make it more active through agents to
help people make decisions more quickly? That's on the governance agent side of things. The next
piece is agent price discovery. So a big problem right now is like all these, you know, AI companies really
struggle to identify how much their solution should cost. And it really is dependent on how
much value that they're providing. And so in the onboarding process of the Near AI Hub,
we would like to add a piece for you to monetize your agent. But to monetize it properly, you need
to discover the utility and price of that agent.
And so working with a cool team that's called Nevermind to help address this problem.
I've been talking to them a lot this week on how to do so.
More to come on that.
Another really hard problem to solve.
Fortunately, I'm not the only one to solve these problems.
There are amazing teams out there with many more employees that are highly more qualified than i to do so my goal is just get them integrated into the near ai hub and you know made available for all the builders out there so that's on agent price discovery and i have a long list
by the way i'm very it's it's been a crazy couple weeks uh next is uh really want to add near intents to a Coinbase, the Coinbase Commerce on ramp.
Because right now when you want to on ramp from Coinbase USDC from Coinbase to to Solana through base, sorry, Coinbase on-ramp, you can actually add the intent network in the middle of it, essentially swap that base USDC for your Solana USDC or near USDC or anything like that to essentially enable interoperability across every chain, which is pretty cool for an on-ramp.
every chain, which is pretty cool for an on-ramp.
And so instead of, right now, my main interest for that
for the near side is so we can easily get near agents access
to an easy USDC on-ramp with very, very low fees.
But it just so happens that doing so will actually enable
USDC on-ramp support through an app like Coinbase
if we can figure it out and work with them to make it happen.
I don't want to over promise here. We're still like cooking on the architecture for everything.
So yeah, USDC, Coinbase on-ramp, all chains that support ECDSA signatures. So that's Bitcoin,
Dogecoin, Ethereum, every L2, pretty much everything that's not Solana and Ton.
pretty much everything that's not Solana and Ton.
So moving on, there's more.
Setting up posts for the New AI LinkedIn account.
I hate LinkedIn, but we need to post there
because the AI community is on LinkedIn a lot of times.
So setting that up with Zahid this week, which is exciting.
So expect more content from the New AI LinkedIn account.
And then not really related to New AI at all, but maybe in the future, who knows?
I run a nonprofit.
We start blockchain development courses at universities.
Been doing this for about seven years now.
They ran an amazing hacker house in Argentina.
We're very focused on the Latin American market.
And that was just a huge success during Crecimiento.
Shout out to the Crecimiento team of bringing crypto education and adoption
to Latin America, specifically Argentina.
Really like what they're doing.
And this is an evergreen market.
So if we're building AI agents and assistants
to streamline governance and everything else,
this is a really great market to do so.
And that's it on some of the stuff I'm working on.
I also went to the doctor
for the first time in a long time, which was great. So be healthy. Go to the doctor if you can.
And that's all I got. So thank you all for joining. We do this every week. Make sure to
like the Near AI Twitter account. This is where everything gets live streamed. And for the future,
anyone who is joining, be sure to stream to your audiences.
This is a great way to get more eyes.
So thank you all for joining and hope to see you next week.
